Gwanghyun Kim

PhD student, Seoul National University

Joined

May 2021

Names

Gwanghyun Kim (Preferred)

Gwanghyun Bradley Kim

Emails

****@kaist.ac.kr (Confirmed)

****@snu.ac.kr (Confirmed)

****@google.com (Confirmed)

Personal Links

Career & Education History

PhD student

Seoul National University (snu.ac.kr)

2022 – Present

Research Scientist Intern

NVIDIA (nvidia.com)

2024 – 2024

Student Researcher

Google (google.com)

2023 – 2024

MS student

Korea Advanced Institute of Science and Technology (kaist.ac.kr)

2020 – 2022

Undergrad student

Yonsei University (yonsei.ac.kr)

2014 – 2020

Advisors, Relations & Conflicts

PhD Advisor

Se Young Chun

2022 – Present

MS Advisor

Jong Chul Ye

2020 – 2022

Expertise

Computer vision

Present

Generative models

Present

Diffusion models

Present

Transformer

Present

Multi-modal learning

Present

Machine leaerning

Present

Artificial intelligence

Present

Publications

Human Interaction-Aware 3D Reconstruction from a Single Image
Gwanghyun Kim, Junghun James Kim, Suh Yoon Jeon, Jason Park, Se Young Chun
- PhysHuman Workshop @ CVPR 2026 Oral
- Readers: Everyone
PersonaCraft: Personalized and Controllable Full-Body Multi-Human Scene Generation Using Occlusion-Aware 3D-Conditioned Diffusion
Gwanghyun Kim, Suh Yoon Jeon, Seunggyu Lee, Se Young Chun
- International Conference on Computer Vision, ICCV 2025
- Readers: Everyone
World Action Models are Zero-shot Policies
Seonghyeon Ye, Yunhao Ge, Kaiyuan Zheng, Shenyuan Gao, Sihyun Yu, George Kurian, Suneel Indupuru, You Liang Tan, Chuning Zhu, Jiannan Xiang, Ayaan Naveed Malik, Kyungmin Lee, William Liang, Nadun Ranawaka Arachchige, Jiasheng Gu, Yinzhen Xu, Guanzhi Wang, Fengyuan Hu, Avnish Narayan, Johan Bjorck et al. (16 additional authors not shown)
- ICLR 2026 Workshop World Models
- Readers: Everyone
HUG3D: Human Group-Aware 3D Reconstruction from a Single Image with Physical Interaction
Gwanghyun Kim, Junghun James Kim, Suh Yoon Jeon, Jason Park, Se Young Chun
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Masked, Regularized Fidelity With Diffusion Models For Highly Ill-posed Inverse Problems
Haechang Lee, Hyunwoo Lee, Dong Ju Mun, Kyung Chul Lee, Seongmin Hong, Gwanghyun Kim, Seung Ah Lee, Se Young Chun
- Submitted to ICLR 2025
- Readers: Everyone
A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation
Gwanghyun Kim, Alonso Martinez, Yu-Chuan Su, Brendan Jou, Jose Lezama, Agrim Gupta, Lijun Yu, Lu Jiang, Aren Jansen, Jacob C Walker, Krishna Somandepalli
- NeurIPS 2024 poster
- Readers: Everyone
Large Scene Synthesis Controlled With Detailed Text Using View-wise Conditional Joint Diffusion With Hierarchical Spatial Controls
Gwanghyun Kim, Dong Un Kang, Hoigi Seo, Hayeon Kim, Se Young Chun
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation
Gwanghyun Kim, Taesung Kwon, Jong Chul Ye
- 2022 (modified: 14 Nov 2022)
- CVPR 2022
- Readers: Everyone
Multi-task vision transformer using low-level chest X-ray feature corpus for COVID-19 diagnosis and severity quantification
Sangjoon Park, Gwanghyun Kim, Yujin Oh, Joon Beom Seo, Sang Min Lee, Jin Hwan Kim, Sungjun Moon, Jae-Kwang Lim, Jong Chul Ye
- 2022 (modified: 14 Nov 2022)
- Medical Image Anal. 2022
- Readers: Everyone
AI can evolve without labels: self-evolving vision transformer for chest X-ray diagnosis through knowledge distillation
Sangjoon Park, Gwanghyun Kim, Yujin Oh, Joon Beom Seo, Sang Min Lee, Jin Hwan Kim, Sungjun Moon, Jae-Kwang Lim, Chang Min Park, Jong Chul Ye
- 2022 (modified: 14 Nov 2022)
- CoRR 2022
- Readers: Everyone

View all 18 publications

Co-Authors

View all 71 co-authors